测试环境
操作系统：CentOS Linux release 7.7.1908 (Core)
数据库：PostgreSQL 9.6.12
一、操作系统配置(pg1 && pg2 && pg3)
- 禁用防火墙、selinux
- 同步系统时间
- 修改hosts文件
# more /etc/hosts
127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4
::1 localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.10.176 pg1
192.168.10.177 pg2
192.168.10.178 pg3
192.168.10.170 vip-master
192.168.10.171 vip-slave
- 配置系统参数
# vim /etc/security/limits.conf
* soft stack 10240
* hard stack 10240
* soft nofile 131072
* hard nofile 131072
* soft nproc 131072
* hard nproc 131072
* soft core unlimited
* hard core unlimited
# vim /etc/sysctl.conf
kernel.sem = 50100 64128000 50100 1280
# sysctl -p
二、 安装高可用集群包(pg1 && pg2 && pg3)
- 安装集群包
# yum install -y pacemaker corosync pcs ipvsadm
- 启用pcsd服务
# systemctl start pcsd
# systemctl enable pcsd
# systemctl enable corosync
# systemctl enable pacemaker
- 设置hacluster用户密码
# echo hacluster|passwd hacluster --stdin
- 集群认证(在任一节点上执行)
# pcs cluster auth -u hacluster -p hacluster pg1 pg2 pg3
pg3: Authorized
pg2: Authorized
pg1: Authorized
#
- 同步配置(在任一节点上执行)
# pcs cluster setup --last_man_standing=1 --name pgcluster pg1 pg2 pg3
Destroying cluster on nodes: pg1, pg2, pg3...
pg1: Stopping Cluster (pacemaker)...
pg3: Stopping Cluster (pacemaker)...
pg2: Stopping Cluster (pacemaker)...
pg2: Successfully destroyed cluster
pg1: Successfully destroyed cluster
pg3: Successfully destroyed cluster
Sending 'pacemaker_remote authkey' to 'pg1', 'pg2', 'pg3'
pg2: successful distribution of the file 'pacemaker_remote authkey'
pg1: successful distribution of the file 'pacemaker_remote authkey'
pg3: successful distribution of the file 'pacemaker_remote authkey'
Sending cluster config files to the nodes...
pg1: Succeeded
pg2: Succeeded
pg3: Succeeded
Synchronizing pcsd certificates on nodes pg1, pg2, pg3...
pg3: Success
pg2: Success
pg1: Success
Restarting pcsd on the nodes in order to reload the certificates...
pg3: Success
pg2: Success
pg1: Success
#
- 启动集群(在任一节点上执行)
# pcs cluster start --all
pg1: Starting Cluster (corosync)...
pg2: Starting Cluster (corosync)...
pg3: Starting Cluster (corosync)...
pg1: Starting Cluster (pacemaker)...
pg3: Starting Cluster (pacemaker)...
pg2: Starting Cluster (pacemaker)...
#
三、安装PostgreSQL数据库(pg1 && pg2 && pg3)
- 安装PG
数据库版本：pg 11.x以下版本
# yum install gcc-c++ readline-devel zlib-devel
# tar zxvf postgresql-9.6.tar.gz
# cd postgresql-9.6
# ./configure --prefix=/opt/PostgreSQL/9.6/
# make -j 2
# make install
- 配置用户、数据目录(pg1 && pg2 && pg3)
# useradd postgres
# passwd postgres
# vim /home/postgres/.bash_profile
添加：
export PGDATA=/opt/PostgreSQL/9.6/data
export PATH=/opt/PostgreSQL/9.6/bin:$PATH
# mkdir /opt/PostgreSQL/9.6/data
# chown postgres.postgres /opt/PostgreSQL/9.6/data
# chmod 700 /opt/PostgreSQL/9.6/data
- 主节点(pg1)
# su - postgres
$ initdb -D /opt/PostgreSQL/9.6/data
$ cd /opt/PostgreSQL/9.6/data
- 配置数据库参数
#vim postgresql.conf
hot_standby=on #pg10前的版本需主动开启该参数
listen_addresses = '*'
wal_level = logical
wal_log_hints = on
max_wal_size = 10GB
min_wal_size = 80MB
checkpoint_completion_target = 0.9
archive_mode = on
archive_command = '/bin/true'
wal_keep_segments = 1000
synchronous_standby_names = ''
hot_standby_feedback = on
logging_collector = on
log_filename = 'postgresql-%a.log'
log_truncate_on_rotation = on
log_rotation_size = 0
log_min_duration_statement = 0
log_checkpoints = on
log_connections = on
log_disconnections = on
log_line_prefix = '%t [%p]: db=%d,user=%u,app=%a,client=%h '
log_lock_waits = on
log_temp_files = 0
log_autovacuum_min_duration = 0
lc_messages = 'en_US.UTF-8'
#vim pg_hba.conf
# TYPE DATABASE USER ADDRESS METHOD
# "local" is for Unix domain socket connections only
local all all trust
# IPv4 local connections:
host all all 127.0.0.1/32 md5
host all all 0.0.0.0/0 md5
# IPv6 local connections:
#host all all ::1/128 trust
# Allow replication connections from localhost, by a user with the
# replication privilege.
local replication all trust
host replication all 127.0.0.1/32 md5
host replication repluser 192.168.10.0/24 md5
- 启动master数据库
[root@pg1 ~]# su - postgres
[postgres@pg1 ~]$
[postgres@pg1 ~]$ pg_ctl start -D /opt/PostgreSQL/9.6/data
- 创建复制用户
postgres=# create user repluser with replication password 'repluser';
CREATE ROLE
postgres=# \du
List of roles
Role name | Attributes | Member of
-----------+------------------------------------------------------------+-----------
postgres | Superuser, Create role, Create DB, Replication, Bypass RLS | {}
repluser | Replication | {}
postgres=#
- 创建slave(pg2 && pg3)
# su - postgres
$ pg_basebackup -h pg1 -U repluser -p 5432 -D /opt/PostgreSQL/9.6/data --wal-method=stream --checkpoint=fast --progress --verbose
- 停止master(pg1)
[postgres@pg1 data]$ pg_ctl stop -D /opt/PostgreSQL/9.6/data
waiting for server to shut down.... done
server stopped
[postgres@pg1 data]$ pg_ctl status -D /opt/PostgreSQL/9.6/data
pg_ctl: no server running
[postgres@pg1 data]$
注意事项：
数据库无需配置自启动，由集群软件自动拉起
四、配置集群资源
#vim cluster_setup.sh
pcs cluster cib pgsql_cfg
pcs -f pgsql_cfg property set no-quorum-policy="ignore"
pcs -f pgsql_cfg property set stonith-enabled="false"
pcs -f pgsql_cfg resource defaults resource-stickiness="INFINITY"
pcs -f pgsql_cfg resource defaults migration-threshold="3"
#### vip-master ###
pcs -f pgsql_cfg resource create vip-master IPaddr2 ip="192.168.10.170" cidr_netmask="24" \
op start timeout="60s" interval="0s" on-fail="restart" \
op monitor timeout="60s" interval="10s" on-fail="restart" \
op stop timeout="60s" interval="0s" on-fail="block"
#### vip-slave ###
pcs -f pgsql_cfg resource create vip-slave IPaddr2 ip="192.168.10.171" cidr_netmask="24" \
op start timeout="60s" interval="0s" on-fail="restart" \
op monitor timeout="60s" interval="10s" on-fail="restart" \
op stop timeout="60s" interval="0s" on-fail="block"
#### pgsql resource ####
pcs -f pgsql_cfg resource create pgsql pgsql \
pgctl="/opt/PostgreSQL/9.6/bin/pg_ctl" \
psql="/opt/PostgreSQL/9.6/bin/psql" \
pgdata="/opt/PostgreSQL/9.6/data/" \
config="/opt/PostgreSQL/9.6/data/postgresql.conf" \
rep_mode="sync" node_list="pg1 pg2 pg3" master_ip="192.168.10.170" \
repuser="repluser" \
primary_conninfo_opt="password=repluser \
keepalives_idle=60 keepalives_interval=5 keepalives_count=5" \
restart_on_promote='true' \
op start timeout="60s" interval="0s" on-fail="restart" \
op monitor timeout="60s" interval="4s" on-fail="restart" \
op monitor timeout="60s" interval="3s" on-fail="restart" role="Master" \
op promote timeout="60s" interval="0s" on-fail="restart" \
op demote timeout="60s" interval="0s" on-fail="stop" \
op stop timeout="60s" interval="0s" on-fail="block"
#### setting master #####
pcs -f pgsql_cfg resource master pgsql-cluster pgsql master-max=1 master-node-max=1 clone-max=3 clone-node-max=1 notify=true
#### master group #####
pcs -f pgsql_cfg resource group add master-group vip-master
#### slave group #####
pcs -f pgsql_cfg resource group add slave-group vip-slave
#### master group setting #####
pcs -f pgsql_cfg constraint colocation add master-group with master pgsql-cluster INFINITY
pcs -f pgsql_cfg constraint order promote pgsql-cluster then start master-group symmetrical=false score=INFINITY
pcs -f pgsql_cfg constraint order demote pgsql-cluster then stop master-group symmetrical=false score=0
#### slave-group setting #####
pcs -f pgsql_cfg constraint colocation add slave-group with slave pgsql-cluster INFINITY
pcs -f pgsql_cfg constraint order promote pgsql-cluster then start slave-group symmetrical=false score=INFINITY
pcs -f pgsql_cfg constraint order demote pgsql-cluster then stop slave-group symmetrical=false score=0
#### push config ####
pcs cluster cib-push pgsql_cfg
#chmod +x cluster_setup.sh
#sh cluster_setup.sh
五、集群状态检查常用命令
#pcs status corosync
Membership information
----------------------
Nodeid Votes Name
1 1 pg1 (local)
2 1 pg2
3 1 pg3
#pcs property list
Cluster Properties:
cluster-infrastructure: corosync
cluster-name: pgcluster
dc-version: 1.1.23-1.el7_9.1-9acf116022
have-watchdog: false
last-lrm-refresh: 1614233039
no-quorum-policy: ignore
stonith-enabled: false
Node Attributes:
pg1: pgsql-data-status=LATEST
pg2: pgsql-data-status=STREAMING|SYNC
pg3: pgsql-data-status=STREAMING|ASYNC
#pcs resource show
Master/Slave Set: pgsql-cluster [pgsql]
Masters: [ pg1 ]
Slaves: [ pg2 pg3 ]
Resource Group: master-group
vip-master (ocf::heartbeat:IPaddr2): Started pg1
Resource Group: slave-group
vip-slave (ocf::heartbeat:IPaddr2): Started pg2
#crm_mon -Arf -1
Stack: corosync
Current DC: pg1 (version 1.1.23-1.el7_9.1-9acf116022) - partition with quorum
Last updated: Thu Feb 25 17:43:35 2021
Last change: Thu Feb 25 14:05:07 2021 by root via crm_attribute on pg1
3 nodes configured
5 resource instances configured
Online: [ pg1 pg2 pg3 ]
Full list of resources:
Master/Slave Set: pgsql-cluster [pgsql]
Masters: [ pg1 ]
Slaves: [ pg2 pg3 ]
Resource Group: master-group
vip-master (ocf::heartbeat:IPaddr2): Started pg1
Resource Group: slave-group
vip-slave (ocf::heartbeat:IPaddr2): Started pg2
Node Attributes:
* Node pg1:
+ master-pgsql : 1000
+ pgsql-data-status : LATEST
+ pgsql-master-baseline : 000000000C000098
+ pgsql-status : PRI
* Node pg2:
+ master-pgsql : 100
+ pgsql-data-status : STREAMING|SYNC
+ pgsql-status : HS:sync
* Node pg3:
+ master-pgsql : -INFINITY
+ pgsql-data-status : STREAMING|ASYNC
+ pgsql-status : HS:async
Migration Summary:
* Node pg1:
* Node pg2:
* Node pg3:
- 常用管理命令
pcs status //查看集群状态
pcs resource show //查看资源
pcs resource create ClusterIP IPaddr2 ip=192.168.0.120 cidr_netmask=32 //创建一个虚拟IP资源
pcs resource cleanup //xx表示虚拟资源名称，当集群有资源处于unmanaged的状态时，可以用这个命令清理掉失败的信息，然后重置资源状态
pcs resource list //查看资源列表
pcs resource restart //重启资源
pcs resource enable //启动资源
pcs resource disable //关闭资源
pcs resource delete //删除资源
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
